Abstract: A method, computer program product, and computing system for dynamically adjusting the number of emitted tokens per frame in speech processing systems operating with large stride values.

Abstract: A method, computer program product, and computing system for determining a stride value for a first machine learning model. Transfer learning from the first machine learning model to a second machine learning model is performed, wherein the second machine learning model is an online streaming machine learning model. A spectral pooling layer is inserted into the second machine learning model using the stride value. The second machine learning model is trained with the spectral pooling layer.

Abstract: A method, computer program product, and computing system for dividing a speech signal into a plurality of chunks. A first context window is defined with a first period of past context for processing the plurality of chunks with a neural network of a speech processing system. The neural network is trained using the first context window. A second context window is defined with a first period of past context for processing the plurality of chunks with the neural network. The neural network is trained using the second context window.

Abstract: A method, computer program product, and computing system for dividing a speech signal into a plurality of chunks. A context window is defined for processing a chunk of the plurality of chunks using a neural network of a speech processing system. A processing load associated with the speech processing system is determined. The context window is dynamically adjusted based upon, at least in part, the processing load associated with the speech processing system.

Abstract: An end-to-end automatic speech recognition (ASR) system includes: a first encoder configured for close-talk input captured by a close-talk input mechanism; a second encoder configured for far-talk input captured by a far-talk input mechanism; and an encoder selection layer configured to select at least one of the first and second encoders for use in producing ASR output. The selection is made based on at least one of short-time Fourier transform (STFT), Mel-frequency Cepstral Coefficient (MFCC) and filter bank derived from at least one of the close-talk input and the far-talk input. If signals from both the close-talk input mechanism and the far-talk input mechanism are present for a speech segment, the encoder selection layer dynamically selects between the close-talk encoder and the far-talk encoder to select the encoder that better recognizes the speech segment. An encoder-decoder model is used to produce the ASR output.

Abstract: A method, computer program product, and computing system for inserting a spectral pooling layer into a neural network of a speech processing system. An output of a hidden layer of the neural network is filtered using the spectral pooling layer with a non-integer stride. The filtered output is provided to a subsequent hidden layer of the neural network.

Abstract: A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trained to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.

Abstract: A method estimates source signals from a mixture of source signals by first training an analysis model and a reconstruction model using training data. The analysis model is applied to the mixture of source signals to obtain an analysis representation of the mixture of source signals, and the reconstruction model is applied to the analysis representation to obtain an estimate of the source signals, wherein the analysis model utilizes an analysis linear basis representation, and the reconstruction model utilizes a reconstruction linear basis representation.

Abstract: A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trined to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.

Abstract: A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trained to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.

Abstract: A method for reconstructing at least one target signal comprises determining a first set of feature vectors from the input signal, the first set of feature vectors forming a non-negative input matrix; determining a second set of feature vectors, the second set of feature vectors forming a non-negative noise matrix; decomposing the input matrix into a sum of a first matrix and a second matrix, the first matrix representing a product of a non-negative bases matrix and a non-negative weight matrix, and the second matrix representing a combination of the noise matrix and a noise weight vector; and reconstructing the at least one target signal based on the non-negative bases matrix and the non-negative weight matrix.

Abstract: The present invention relates to an apparatus for improving a perception of a sound signal, the apparatus comprising: a separation unit configured to separate the sound signal into at least one speech component and at least one noise component; and a spatial rendering unit configured to generate an auditory impression of the at least one speech component at a first virtual position with respect to a user, when output via a transducer unit, and of the at least one noise component at a second virtual position with respect to the user, when output via the transducer unit.

Abstract: A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trined to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.

Abstract: A method estimates source signals from a mixture of source signals by first training an analysis model and a reconstruction model using training data. The analysis model is applied to the mixture of source signals to obtain an analysis representation of the mixture of source signals, and the reconstruction model is applied to the analysis representation to obtain an estimate of the source signals, wherein the analysis model utilizes an analysis linear basis representation, and the reconstruction model utilizes a reconstruction linear basis representation.

Abstract: A method for reconstructing at least one target signal comprises determining a first set of feature vectors from the input signal, the first set of feature vectors forming a non-negative input matrix; determining a second set of feature vectors, the second set of feature vectors forming a non-negative noise matrix; decomposing the input matrix into a sum of a first matrix and a second matrix, the first matrix representing a product of a non-negative bases matrix and a non-negative weight matrix, and the second matrix representing a combination of the noise matrix and a noise weight vector; and reconstructing the at least one target signal based on the non-negative bases matrix and the non-negative weight matrix.